© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41269
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite

    social connection and belonging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     l
    0.49
     dress
    0.48
     vuurp
    0.47
     admire
    0.45
     pjes
    0.44
     wollten
    0.44
     //.
    0.44
    rei
    0.44
     vn
    0.43
    ite
    0.43
    POSITIVE LOGITS
    Enfin
    0.50
    Ве
    0.50
    Dictionaries
    0.48
    Josef
    0.48
    ח
    0.48
    ヨ
    0.48
     बेटर
    0.48
    дентификаторы
    0.47
    የት
    0.47
     컴퓨
    0.47
    Activations Density 0.000%

    No Known Activations